network-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest and process data from external files such as 'resources/implementation-playbook.md' and other files within the 'references/', 'examples/', and 'scripts/' directories, which introduces a potential attack surface.
- Ingestion points: The workflow explicitly relies on loading external content from files in the 'resources/', 'references/', 'examples/', and 'scripts/' directories to execute network engineering tasks (SKILL.md).
- Boundary markers: Absent. There are no specific delimiters or instructions provided to the agent to treat data from these external files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses a broad range of capabilities, including the use of network diagnostic tools (tcpdump, nmap, openssl), infrastructure management (Terraform, Ansible), and network automation libraries (Netmiko, NAPALM) (SKILL.md).
- Sanitization: Absent. The skill does not include instructions for the agent to sanitize or validate content loaded from external files before processing or execution.
Audit Metadata